Systems and methods for generating images for identifying diseases

Abstract

Systems and methods for generating images for identifying diseases are provided. In one embodiment, a method comprises receiving a first digital radiography (DR) image of at least a portion of a body of a patient, receiving a second DR image of the at least a portion of a body of a patient, the first DR image being captured at a different energy level than the second DR image, and determining common control point locations for both the first and second DR images. The method further comprises generating an optimized DR image by moving portions of a selected one of the first and second DR images with its associated control points to locations that correspond to similar portions of the other of the first and second DR images, applying deformable transformation to one of the first and second DR images and performing a log subtraction on the first and second DR image to generate a dual-energy digital radiography (DEDR) image.

1. A method for generating images for identifying diseases, the method comprising:
 receiving a first digital radiography (DR) X-ray image of at least a portion of a body of a patient; 
 receiving a second DR X-ray image of the at least a portion of a body of a patient, the first X-ray image being captured at a different energy level than the second DR X-ray image; 
 determining common control point locations for both the first and second DR X-ray images; 
 generating an optimized DR X-ray image by moving portions of a selected one of the first and second DR X-ray images with its associated control points to locations that correspond to similar portions of the other of the first and second DR X-ray images; 
 applying deformable transformation to one of the first and second DR X-ray images; and 
 performing a log subtraction on the first and second DR X-ray image to generate a dual-energy digital radiography (DEDR) image. 
 
     
     
       2. The method of  claim 1 , wherein the performing a log subtraction on the first and second DR X-ray image to generate a DEDR image comprises performing a bone log subtraction on the first and second DR X-ray image to generate a bone image. 
     
     
       3. The method of  claim 2 , further comprising performing a soft tissue log subtraction on the first and second DR X-ray image to generate a soft tissue image. 
     
     
       4. The method of  claim 1 , wherein the determining common control point locations for both the first and second DR X-ray images comprises dividing the first and second DR X-ray image into a plurality of grids, such that each grid of the first DR X-ray image has an associated grid in the second DR X-ray image, and determining a common center point for each of the plurality of grids for both the first and second DR X-ray image. 
     
     
       5. The method of  claim 1 , wherein the determining common control point locations for both the first and second DR X-ray images comprises determining common edge features of the first and second DR X-ray images. 
     
     
       6. The method of  claim 1 , wherein the applying deformable transformation to one of the first and second DR X-ray images comprises performing one of a TPS algorithm and a B-spline algorithm on the one of the first and second DR X-ray images. 
     
     
       7. The method of  claim 1 , further comprising receiving a three-dimensional computer tomography (CT) image and registering the three-dimensional CT image with the DEDR image. 
     
     
       8. The method of  claim 7 , further comprising:
 performing a 3-dimensional (3D) translation and rotation on the CT image; 
 projecting the CT image onto an image plane to generate a 2-dimensional (2D) digitally reconstructed radiography (DRR) image; 
 performing a 2D transformation on the 2D DRR image; 
 measuring similarities of the 2D DRR with the DEDR image; and 
 optimizing the registration of the 2D DRR with the DEDR image. 
 
     
     
       9. The method of  claim 1 , further comprising reviewing the dual-energy image to detect areas of cardiac calcification. 
     
     
       10. The method of  claim 1 , further comprising reviewing a digitally reconstructed radiography (DRR) image constructed from a three-dimensional computer tomography (CT) image to determine the validity of the detected areas of cardiac calcification in the DEDR image. 
     
     
       11. A computer readable computer having computer executable instructions for performing the method of  claim 1 . 
     
     
       12. A system for generating images for identifying diseases, the system comprising:
 a control point optimization component configured to receive a first digital radiography (DR) X-ray image captured at a first energy level and a second DR X-ray image captured at a second energy level of at least a portion of a body of a patient and configured to optimize a DR X-ray image by moving portions of a selected one of the first and second DR X-ray images to locations that correspond to similar portions of the other of the first and second DR X-ray images; 
 a deformable transformation component that applies a deformable transformation to one of the first and second DR X-ray images; and 
 a log subtraction component that performs a log subtraction on the first and second DR X-ray image to generate a dual-energy digital radiography (DEDR) image. 
 
     
     
       13. The system of  claim 12 , wherein the log subtraction component performs at least one of a bone log subtraction to generate a bone image and a soft tissue log subtraction to generate a soft tissue image. 
     
     
       14. The system of  claim 12 , wherein the control point optimization component is configured to locate common control point locations for both the first and second DR X-ray images by dividing the first and second DR X-ray image into a plurality of grids, such that each grid of the first DR X-ray image has an associated grid in the second DR X-ray image, and determining a common center point for each of the plurality of grids for both the first and second DR X-ray image. 
     
     
       15. The system of  claim 12 , wherein the control point optimization component is configured to locate common control point locations for both the first and second DR X-ray images by determining common edge features of the first and second DR X-ray image. 
     
     
       16. The system of  claim 12 , wherein the deformable transformation component is configured to perform one of a TPS algorithm and a B-spline algorithm on the one of the first and second DR X-ray images.